A Machine Learning Approach for Automated Detection of Critical PCB Flaws in Optical Sensing Systems
Round 1
Reviewer 1 Report
Comments for author File: 
Comments.pdf
English language required moderate editing.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The topic of the paper has certain cutting-edge significance and practical value. The article focuses on the research of PCB defect recognition in optical sensing systems and proposes an improved YOLOV8 object detection algorithm. The author elaborated on the entire system framework for improving YOLOV8, analyzed the specific working mechanism for generating PCB defect target recognition, and trained and optimized the comparison on the dataset. The experimental design was reasonable, the data was rich and accurate, and the conclusion was reliable. The paper adopts standardized analysis, comparative research, experimental testing and validation methods to verify one's own viewpoints and the feasibility of the algorithm. The research methods are relatively scientific, and the research results are helpful in solving relevant problems. It is recommended to accept this article after completing the following minor modifications.
1. What role does the confusion matrix in Figure 12 play in this article.
2. Please carefully check if the legends in the text correspond one by one.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The A Machine Learning Approach for Automated Detection of Critical PCB Flaws in Optical Sensing System, present theory and experiments of a series of circuit used in some sensing applications. However, there is not any concrete application tested in the paper, no any improvement demonstrated. The main results are related to the electronics part but not optics. Therefore, the paper is out of the scope of the journal. Additionally, the novelty of the paper is not clear.
Needs minor improvements
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 3 Report
I understood the aim and idea of the paper more clearly. I think the concept of machine learning used here can be apply for optical sensing, therefore it can be interesting for the readers of the journal
Minor revisions are needed
